• 研究課題をさがす
  • 研究者をさがす
  • KAKENの使い方
  1. 課題ページに戻る

2022 年度 実施状況報告書

Toward New-Generation AI-Based CAD System: Development of Interpretable Deep Learning-Based CAD System for Breast Cancer Diagnosis Using Mammogram

研究課題

研究課題/領域番号 20K08012
研究機関仙台高等専門学校

研究代表者

張 暁勇  仙台高等専門学校, 総合工学科, 准教授 (90722752)

研究分担者 費 仙鳳  東北文化学園大学, 工学部, 准教授 (20620470)
研究期間 (年度) 2020-04-01 – 2024-03-31
キーワードMammograpy / Deep Learning / Explainable AI / Computer-Aided Diagnosis / Lesion Detection
研究実績の概要

The purpose of this research is to develop an interpretable deep learning (DL)-based computer-aided diagnosis (CAD) system for breast cancer diagnosis in mammogram. On the base of the achivement of FY2021, we achived the following progresses in the FY2022.

(1) Experments for evaluation of DL models in lesion detection has been conducted on four mammogram data sets, which were collected in the previous FY.
(2) A new training method, which utilized the clinicians's pixel-wise anotation and saliency maps to improve the DL model acuuracy, was proposed and tested.
(3) Two papers has been published in the related international journals.

現在までの達成度 (区分)
現在までの達成度 (区分)

3: やや遅れている

理由

In the FY2022, the paper publication was progressed smoothly according to the research plan. However, the CAD system development was slightly delayed since the experimental device was unavailable.

(1) Two papers about the DL for medical image analysis have been published in the FY2022. And another paper is still under reviewed currently.
(2) A GPU-equipped computer installation was delayed since the global semiconductor shortage in 2022.

今後の研究の推進方策

According to the research plan, the main research in FY2023 will be focused on the following three tasks.

(1) Installing the GPU-equipped computer and complete the remaining experiments.
(2) Evaluating the accuracy of DL models in comparison with clinicians screening and assessing whether the screening accuracy of clinicians can be improved with the AI-aided system.
(3) A conclusive paper will be submitted to prime international journal.

次年度使用額が生じた理由

Due to the semiconductor shortage, the delivery of GPU-equipped computers for computational purposes is being delayed. As a result, it may not be possible to complete the subsidized project within the designated period.
A GPU device will be installed and remaining experiments will be completed as soon as possibley in the FY2023.

  • 研究成果

    (2件)

すべて 2023 2022

すべて 雑誌論文 (2件) (うち査読あり 2件、 オープンアクセス 2件)

  • [雑誌論文] A 2.5D Deep Learning-Based Method for Drowning Diagnosis Using Post-Mortem Computed Tomography2023

    • 著者名/発表者名
      Zeng Yuwen、Zhang Xiaoyong、Kawasumi Yusuke、Usui Akihito、Ichiji Kei、Funayama Masato、Homma Noriyasu
    • 雑誌名

      IEEE Journal of Biomedical and Health Informatics

      巻: 27 ページ: 1026~1035

    • DOI

      10.1109/jbhi.2022.3225416

    • 査読あり / オープンアクセス
  • [雑誌論文] Improved Tumor Image Estimation in X-Ray Fluoroscopic Images by Augmenting 4DCT Data for Radiotherapy2022

    • 著者名/発表者名
      Shinohara Takumi、Ichiji Kei、Wang Jiaoyang、Homma Noriyasu、Zhang Xiaoyong、Sugita Norihiro、Yoshizawa Makoto
    • 雑誌名

      Journal of Advanced Computational Intelligence and Intelligent Informatics

      巻: 26 ページ: 471~482

    • DOI

      10.20965/jaciii.2022.p0471

    • 査読あり / オープンアクセス

URL: 

公開日: 2023-12-25  

サービス概要 検索マニュアル よくある質問 お知らせ 利用規程 科研費による研究の帰属

Powered by NII kakenhi